[v16,3/7] crash: add generic infrastructure for crash hotplug support

Message ID 20230105151709.1845-4-eric.devolder@oracle.com
State New
Headers
Series crash: Kernel handling of CPU and memory hot un/plug |

Commit Message

Eric DeVolder Jan. 5, 2023, 3:17 p.m. UTC
  CPU and memory change notifications are received in order to
regenerate the elfcorehdr.

To support cpu hotplug, a callback is registered to capture the
CPUHP_AP_ONLINE_DYN online and offline events via
cpuhp_setup_state_nocalls().

To support memory hotplug, a notifier is registered to capture the
MEM_ONLINE and MEM_OFFLINE events via register_memory_notifier().

The cpu callback and memory notifiers call handle_hotplug_event()
which performs needed tasks and then dispatches the event to the
architecture specific arch_crash_handle_hotplug_event(). During the
process, the kexec_lock is held.

Signed-off-by: Eric DeVolder <eric.devolder@oracle.com>
Acked-by: Baoquan He <bhe@redhat.com>
---
 include/linux/crash_core.h |   8 +++
 include/linux/kexec.h      |  12 ++++
 kernel/crash_core.c        | 138 +++++++++++++++++++++++++++++++++++++
 3 files changed, 158 insertions(+)
  

Patch

diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index de62a722431e..a270f8660538 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -84,4 +84,12 @@  int parse_crashkernel_high(char *cmdline, unsigned long long system_ram,
 int parse_crashkernel_low(char *cmdline, unsigned long long system_ram,
 		unsigned long long *crash_size, unsigned long long *crash_base);
 
+#define KEXEC_CRASH_HP_REMOVE_CPU		0
+#define KEXEC_CRASH_HP_ADD_CPU			1
+#define KEXEC_CRASH_HP_REMOVE_MEMORY		2
+#define KEXEC_CRASH_HP_ADD_MEMORY		3
+#define KEXEC_CRASH_HP_INVALID_CPU		-1U
+
+struct kimage;
+
 #endif /* LINUX_CRASH_CORE_H */
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index c8662a48d455..a1838699d7b2 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -33,6 +33,7 @@  extern note_buf_t __percpu *crash_notes;
 #include <linux/compat.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
+#include <linux/highmem.h>
 #include <asm/kexec.h>
 
 /* Verify architecture specific macros are defined */
@@ -371,6 +372,13 @@  struct kimage {
 	struct purgatory_info purgatory_info;
 #endif
 
+#ifdef CONFIG_CRASH_HOTPLUG
+	bool hotplug_event;
+	unsigned int offlinecpu;
+	bool elfcorehdr_index_valid;
+	int elfcorehdr_index;
+#endif
+
 #ifdef CONFIG_IMA_KEXEC
 	/* Virtual address of IMA measurement buffer for kexec syscall */
 	void *ima_buffer;
@@ -500,6 +508,10 @@  static inline int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, g
 static inline void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) { }
 #endif
 
+#ifndef arch_crash_handle_hotplug_event
+static inline void arch_crash_handle_hotplug_event(struct kimage *image) { }
+#endif
+
 #else /* !CONFIG_KEXEC_CORE */
 struct pt_regs;
 struct task_struct;
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 92eb7dc05457..973d7ddff1cf 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -11,6 +11,8 @@ 
 #include <linux/vmalloc.h>
 #include <linux/sizes.h>
 #include <linux/kexec.h>
+#include <linux/memory.h>
+#include <linux/cpuhotplug.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>
@@ -18,6 +20,7 @@ 
 #include <crypto/sha1.h>
 
 #include "kallsyms_internal.h"
+#include "kexec_internal.h"
 
 /* vmcoreinfo stuff */
 unsigned char *vmcoreinfo_data;
@@ -615,3 +618,138 @@  static int __init crash_save_vmcoreinfo_init(void)
 }
 
 subsys_initcall(crash_save_vmcoreinfo_init);
+
+#ifdef CONFIG_CRASH_HOTPLUG
+#undef pr_fmt
+#define pr_fmt(fmt) "crash hp: " fmt
+/*
+ * To accurately reflect hot un/plug changes, the elfcorehdr (which
+ * is passed to the crash kernel via the elfcorehdr= parameter)
+ * must be updated with the new list of CPUs and memories.
+ *
+ * In order to make changes to elfcorehdr, two conditions are needed:
+ * First, the segment containing the elfcorehdr must be large enough
+ * to permit a growing number of resources; the elfcorehdr memory size
+ * is based on NR_CPUS_DEFAULT and CRASH_MAX_MEMORY_RANGES.
+ * Second, purgatory must explicitly exclude the elfcorehdr from the
+ * list of segments it checks (since the elfcorehdr changes and thus
+ * would require an update to purgatory itself to update the digest).
+ */
+static void handle_hotplug_event(unsigned int hp_action, unsigned int cpu)
+{
+	/* Obtain lock while changing crash information */
+	if (kexec_trylock()) {
+
+		/* Check kdump is loaded */
+		if (kexec_crash_image) {
+			struct kimage *image = kexec_crash_image;
+
+			if (hp_action == KEXEC_CRASH_HP_ADD_CPU ||
+				hp_action == KEXEC_CRASH_HP_REMOVE_CPU)
+				pr_debug("hp_action %u, cpu %u\n", hp_action, cpu);
+			else
+				pr_debug("hp_action %u\n", hp_action);
+
+			/*
+			 * When the struct kimage is allocated, it is wiped to zero, so
+			 * the elfcorehdr_index_valid defaults to false. Find the
+			 * segment containing the elfcorehdr, if not already found.
+			 * This works for both the kexec_load and kexec_file_load paths.
+			 */
+			if (!image->elfcorehdr_index_valid) {
+				unsigned long mem;
+				unsigned char *ptr;
+				unsigned int n;
+
+				for (n = 0; n < image->nr_segments; n++) {
+					mem = image->segment[n].mem;
+					ptr = kmap_local_page(pfn_to_page(mem >> PAGE_SHIFT));
+					if (ptr) {
+						/* The segment containing elfcorehdr */
+						if (memcmp(ptr, ELFMAG, SELFMAG) == 0) {
+							image->elfcorehdr_index = (int)n;
+							image->elfcorehdr_index_valid = true;
+						}
+						kunmap_local(ptr);
+					}
+				}
+			}
+
+			if (!image->elfcorehdr_index_valid) {
+				pr_err("unable to locate elfcorehdr segment");
+				goto out;
+			}
+
+			/* Needed in order for the segments to be updated */
+			arch_kexec_unprotect_crashkres();
+
+			/* Flag to differentiate between normal load and hotplug */
+			image->hotplug_event = true;
+
+			/* Now invoke arch-specific update handler */
+			arch_crash_handle_hotplug_event(image);
+
+			/* No longer handling a hotplug event */
+			image->hotplug_event = false;
+
+			/* Change back to read-only */
+			arch_kexec_protect_crashkres();
+		}
+
+out:
+		/* Release lock now that update complete */
+		kexec_unlock();
+	}
+}
+
+static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *v)
+{
+	switch (val) {
+	case MEM_ONLINE:
+		handle_hotplug_event(KEXEC_CRASH_HP_ADD_MEMORY,
+			KEXEC_CRASH_HP_INVALID_CPU);
+		break;
+
+	case MEM_OFFLINE:
+		handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_MEMORY,
+			KEXEC_CRASH_HP_INVALID_CPU);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block crash_memhp_nb = {
+	.notifier_call = crash_memhp_notifier,
+	.priority = 0
+};
+
+static int crash_cpuhp_online(unsigned int cpu)
+{
+	handle_hotplug_event(KEXEC_CRASH_HP_ADD_CPU, cpu);
+	return 0;
+}
+
+static int crash_cpuhp_offline(unsigned int cpu)
+{
+	handle_hotplug_event(KEXEC_CRASH_HP_REMOVE_CPU, cpu);
+	return 0;
+}
+
+static int __init crash_hotplug_init(void)
+{
+	int result = 0;
+
+	if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG))
+		register_memory_notifier(&crash_memhp_nb);
+
+	if (IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		result = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+						   "crash/cpuhp",
+						   crash_cpuhp_online,
+						   crash_cpuhp_offline);
+
+	return result;
+}
+
+subsys_initcall(crash_hotplug_init);
+#endif